[PATCH v4 3/7] padata: dispatch works on different nodes

[Gang Li <gang.li@linux.dev>]

When a group of tasks that access different nodes are scheduled on the
same node, they may encounter bandwidth bottlenecks and access latency.

Thus, numa_aware flag is introduced here, allowing tasks to be
distributed across different nodes to fully utilize the advantage of
multi-node systems.

Signed-off-by: Gang Li <gang.li@linux.dev>
Tested-by: David Rientjes <rientjes@google.com>
---
 include/linux/padata.h |  3 +++
 kernel/padata.c        | 14 ++++++++++++--
 mm/mm_init.c           |  1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 495b16b6b4d7..f79ccd50e7f4 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -137,6 +137,8 @@ struct padata_shell {
  *             appropriate for one worker thread to do at once.
  * @max_threads: Max threads to use for the job, actual number may be less
  *               depending on task size and minimum chunk size.
+ * @numa_aware: Dispatch jobs to different nodes. If a node only has memory but
+ *              no CPU, dispatch its jobs to a random CPU.
  */
 struct padata_mt_job {
 	void (*thread_fn)(unsigned long start, unsigned long end, void *arg);
@@ -146,6 +148,7 @@ struct padata_mt_job {
 	unsigned long		align;
 	unsigned long		min_chunk;
 	int			max_threads;
+	bool			numa_aware;
 };
 
 /**
diff --git a/kernel/padata.c b/kernel/padata.c
index 179fb1518070..10eae3f59203 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -485,7 +485,8 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 	struct padata_work my_work, *pw;
 	struct padata_mt_job_state ps;
 	LIST_HEAD(works);
-	int nworks;
+	int nworks, nid;
+	static atomic_t last_used_nid = ATOMIC_INIT(0);
 
 	if (job->size == 0)
 		return;
@@ -517,7 +518,16 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 	ps.chunk_size = roundup(ps.chunk_size, job->align);
 
 	list_for_each_entry(pw, &works, pw_list)
-		queue_work(system_unbound_wq, &pw->pw_work);
+		if (job->numa_aware) {
+			int old_node = atomic_read(&last_used_nid);
+
+			do {
+				nid = next_node_in(old_node, node_states[N_CPU]);
+			} while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid));
+			queue_work_node(nid, system_unbound_wq, &pw->pw_work);
+		} else {
+			queue_work(system_unbound_wq, &pw->pw_work);
+		}
 
 	/* Use the current thread, which saves starting a workqueue worker. */
 	padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 2c19f5515e36..549e76af8f82 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2231,6 +2231,7 @@ static int __init deferred_init_memmap(void *data)
 			.align       = PAGES_PER_SECTION,
 			.min_chunk   = PAGES_PER_SECTION,
 			.max_threads = max_threads,
+			.numa_aware  = false,
 		};
 
 		padata_do_multithreaded(&job);
-- 
2.20.1